Safe Multisig Skill

Security checks across malware telemetry and agentic risk

Overview

This skill does what it advertises: it operates Safe multisig wallets, but users must treat it as a high-impact financial tool.

Install only if you want an agent to help propose, approve, deploy, or execute Safe transactions. Use a low-privilege signer where possible, keep private keys out of chat, verify the Safe address, chain, nonce, tx hash, RPC URL, and transaction JSON before signing, and pass only transaction files you intentionally selected.

SkillSpector

By NVIDIA

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 92% confidence
Finding: The skill documentation describes scripts that use environment variables, invoke shell commands, and access external networks, but the skill does not declare corresponding permissions. This creates a trust and review gap: an agent or operator may approve or run the skill without understanding that it can read secrets, contact RPC/transaction-service endpoints, and trigger blockchain-affecting operations.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal